Back to Search
Start Over
Guided filter-based multi-scale super-resolution reconstruction
- Source :
- CAAI Transactions on Intelligence Technology (2020)
- Publication Year :
- 2020
- Publisher :
- Wiley, 2020.
-
Abstract
- The learning-based super-resolution reconstruction method inputs a low-resolution image into a network, and learns a non-linear mapping relationship between low-resolution and high-resolution through the network. In this study, the multi-scale super-resolution reconstruction network is used to fuse the effective features of different scale images, and the non-linear mapping between low resolution and high resolution is studied from coarse to fine to realise the end-to-end super-resolution reconstruction task. The loss of some features of the low-resolution image will negatively affect the quality of the reconstructed image. To solve the problem of incomplete image features in low-resolution, this study adopts the multi-scale super-resolution reconstruction method based on guided image filtering. The high-resolution image reconstructed by the multi-scale super-resolution network and the real high-resolution image are merged by the guide image filter to generate a new image, and the newly generated image is used for secondary training of the multi-scale super-resolution reconstruction network. The newly generated image effectively compensates for the details and texture information lost in the low-resolution image, thereby improving the effect of the super-resolution reconstructed image.Compared with the existing super-resolution reconstruction scheme, the accuracy and speed of super-resolution reconstruction are improved.
- Subjects :
- low-resolution image loss
0209 industrial biotechnology
Computer Networks and Communications
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
Iterative reconstruction
Composite image filter
high-resolution image
multiscale super-resolution reconstruction network
Image (mathematics)
020901 industrial engineering & automation
Image texture
guided filter-based multiscale super-resolution reconstruction
Artificial Intelligence
0202 electrical engineering, electronic engineering, information engineering
Computer vision
image texture
super-resolution reconstruction effect
newly generated image
Image resolution
end-to-end super-resolution reconstruction task
multiscale super-resolution network
image filtering
lcsh:Computer software
business.industry
multiscale super-resolution reconstruction method
learning-based super-resolution reconstruction method
lcsh:P98-98.5
Filter (signal processing)
super-resolution reconstruction scheme
image reconstruction
Human-Computer Interaction
guide image filter
lcsh:QA76.75-76.765
Computer Science::Computer Vision and Pattern Recognition
Fuse (electrical)
020201 artificial intelligence & image processing
learning (artificial intelligence)
Computer Vision and Pattern Recognition
Artificial intelligence
guided image filtering
lcsh:Computational linguistics. Natural language processing
business
Scale (map)
Information Systems
image resolution
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- CAAI Transactions on Intelligence Technology (2020)
- Accession number :
- edsair.doi.dedup.....21eae680cadccd21848ddaaa20f067ab